Can LLMs Understand the Implication of Emphasized Sentences in Dialogue?

TL;DR

This paper introduces Emphasized-Talk, a benchmark for evaluating LLMs' ability to understand emphasis in dialogue, revealing that current models perform reasonably but still need improvement in grasping implied meanings.

Contribution

The paper presents a new benchmark with emphasis-annotated dialogue samples and an automatic GPT-4 based evaluation pipeline for assessing LLMs' understanding of emphasis.

Findings

Commercial LLMs outperform open-source models

Current models show limited understanding of emphasis implications

GPT-4 based evaluation correlates well with human judgment

Abstract

Emphasis is a crucial component in human communication, which indicates the speaker's intention and implication beyond pure text in dialogue. While Large Language Models (LLMs) have revolutionized natural language processing, their ability to understand emphasis in dialogue remains unclear. This paper introduces Emphasized-Talk, a benchmark with emphasis-annotated dialogue samples capturing the implications of emphasis. We evaluate various LLMs, both open-source and commercial, to measure their performance in understanding emphasis. Additionally, we propose an automatic evaluation pipeline using GPT-4, which achieves a high correlation with human rating. Our findings reveal that although commercial LLMs generally perform better, there is still significant room for improvement in comprehending emphasized sentences.